ShapBPT：基于数据感知二进制划分树的图像特征归因
ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Trees
AI总结：
本文提出ShapBPT，一种基于层次Shapley公式的数据感知图像可视化方法，通过多尺度二进制划分树结构提升图像特征归因的效率与语义意义。
摘要：
像素级特征归因是计算机视觉可解释AI（XCV）中的重要工具，提供图像特征如何影响模型预测的视觉洞察。层次Shapley值的Owen公式已被广泛用于解释机器学习模型及其学习表示。然而，现有层次Shapley方法未利用图像数据的多尺度结构，导致收敛缓慢且与实际形态特征对齐不足。此外，没有先前的Shapley方法利用数据感知层次结构进行计算机视觉任务，留下了解构结构视觉数据模型可解释性方面的空白。为了解决这一问题，本文引入ShapBPT，一种基于层次Shapley公式的新型数据感知XCV方法。ShapBPT将Shapley系数分配给针对图像设计的多尺度层次结构，即二进制划分树（BPT）。通过使用这种数据感知的层次划分，ShapBPT确保特征归因与图像内在形态对齐，有效优先考虑相关区域并减少计算开销。这一进展将层次Shapley方法与图像数据连接起来，提供了一种更高效且具有语义意义的视觉可解释性方法。实验结果证实了ShapBPT的有效性，证明其在图像结构上的对齐优于现有XCV方法，并且20名受试者的研究表明，ShapBPT的解释更受人类偏好。
英文摘要：
Pixel-level feature attributions are an important tool in eXplainable AI for Computer Vision (XCV), providing visual insights into how image features influence model predictions. The Owen formula for hierarchical Shapley values has been widely used to interpret machine learning (ML) models and their learned representations. However, existing hierarchical Shapley approaches do not exploit the multiscale structure of image data, leading to slow convergence and weak alignment with the actual morphological features. Moreover, no prior Shapley method has leveraged data-aware hierarchies for Computer Vision tasks, leaving a gap in model interpretability of structured visual data. To address this, this paper introduces ShapBPT, a novel data-aware XCV method based on the hierarchical Shapley formula. ShapBPT assigns Shapley coefficients to a multiscale hierarchical structure tailored for images, the Binary Partition Tree (BPT). By using this data-aware hierarchical partitioning, ShapBPT ensures that feature attributions align with intrinsic image morphology, effectively prioritizing relevant regions while reducing computational overhead. This advancement connects hierarchical Shapley methods with image data, providing a more efficient and semantically meaningful approach to visual interpretability. Experimental results confirm ShapBPT's effectiveness, demonstrating superior alignment with image structures and improved efficiency over existing XCV methods, and a 20-subject user study confirming that ShapBPT explanations are preferred by humans.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
